About Me

I am a third year Ph.D. student at the Bernoulli Institute, University of Groningen, where my research focuses on the privacy and security of large language models (LLMs). My doctoral work is conducted as part of the LESSEN project, which aims to develop low-resource conversational assistants. I am supervised by Fatih Turkman and Suzan Verberne.

My research focuses on privacy risks in LLMs, particularly issues caused by memorization of sensitive training data. I study data extraction attacks that can recover personal or proprietary information from model outputs, aiming to understand how and why these vulnerabilities arise. In parallel, I explore defense strategies such as privacy preserving training methods and machine unlearning to reduce leakage and improve robustness. Overall, my work contributes to building more private and trustworthy language models for real world deployment.